Activity Overview
Ice-creamery “Sundae” has seasonal sales figures for three consecutive years. Students are required to predict the expected sales for a fourth year. This is done using two approaches, the first without deseaonalising the data, the second with the deseasonalised data, the aim it to demonstrate the importance of deseasonlising.
Watch the Activity Tutorial
Objectives
Seasonal adjustment including the use and interpretation of seasonal indices and their calculation using seasonal and yearly means.
Modelling trend by fitting a least squares line to a time series with time as the explanatory variable (data de-seasonalised where necessary), and the use of the model to make forecasts (with re-seasonalisation where necessary) including consideration of the possible limitations of fitting a linear model and the limitations of extending into the future.
Vocabulary
- Seasonalise
- Deseasonalise
- Indices
- Widget
- Smoothing
- Linear Regression
About the Lesson
To help students understand why data needs to be deseasonlised, they generate a linear regression model for the seasonal data, which of course turns out to be a really lousy predictor for future sales. This approach makes the act of deseasonalising relevant.